Ensemble Machine Learning Models for Predicting Hospital Readmission Rates
DOI:
https://doi.org/10.5281/ijurd.v1i2.55Keywords:
Hospital Readmission, Ensemble Learning, Random Forest, XGBoost, Healthcare Analytics, Predictive ModelingAbstract
Hospital readmissions are a critical concern in healthcare management. This study evaluates ensemble learning techniques using electronic health records to predict 30-day readmission risks. A dataset of over 50,000 patient records is analyzed using Random Forest, Gradient Boosting, and XGBoost models. Feature engineering techniques are applied to identify key predictors such as length of stay, comorbidities, and prior admissions. The proposed ensemble achieves an AUC of 0.81, outperforming individual models. Explainability is incorporated using SHAP values to improve clinical trust. The model enables proactive intervention strategies and supports decision-making processes in hospitals.References
Aman, & Chhillar, R. S. (2021). Analyzing predictive algorithms in data mining for cardiovascular disease using WEKA tool. International Journal of Advanced Computer Science and Applications, 12(8), 144–150.
Aman, & Chhillar, R. S. (2022). Analyzing three predictive algorithms for diabetes mellitus against the Pima Indians dataset. ECS Transactions, 107(1), 2697.
Aman, & Chhillar, R. S. (2023). Optimized stacking ensemble for early-stage diabetes mellitus prediction. International Journal of Electrical and Computer Engineering, 13(6).
Aman, & Chhillar, R. S. (2024). A stacking-based hybrid model with random forest as meta-learner for diabetes mellitus prediction. International Journal of Machine Learning, 14(2), 54–58.
Aman, Chhillar, R. S., & Chhillar, U. (2023). Disease prediction in healthcare: An ensemble learning perspective.
Aman, Chhillar, R. S., & Chhillar, U. (2024). Machine learning in the battle against COVID-19: Predictive models and future directions. Future Computing Technologies for Sustainable Development (NCFCTSD-24).
Aman, Chhillar, R. S., & Chhillar, U. (2025). Machine learning and chronic kidney disease: Towards early prediction and diagnosis. Emerging Trends in Engineering, Commerce, Management and Hospitality Management in the Digital Age for a Sustainable Future.
Darolia, A., Chhillar, R. S., Alhussein, M., Dalal, S., Aurangzeb, K., & Lilhore, U. K. (2024). Enhanced cardiovascular disease prediction through self-improved Aquila optimized feature selection in quantum neural network and LSTM model. Frontiers in Medicine, 11, 1414637.
Aman, C. R. (2020). Disease predictive models for healthcare by using data mining techniques: State of the art. SSRG International Journal of Engineering Trends and Technology, 68(10). Available: https://www.researchgate.net/profile/Aman-Darolia/publication/345397957_Disease_Predictive_Models_for_Healthcare_by_using_Data_Mining_Techniques_State_of_the_Art/links/63b599fa03aad5368e64aa42/Disease-Predictive-Models-for-Healthcare-by-using-Data-Mining-Techniques-State-of-the-Art.pdf
Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140.
Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139.
Dietterich, T. G. (2000). Ensemble methods in machine learning. Multiple Classifier Systems.
Zhou, Z. H. (2012). Ensemble methods: Foundations and algorithms. CRC Press.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Mona Shah, Geeta Gupta
This work is licensed under a Creative Commons Attribution 4.0 International License.
